Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning

TL;DR

This paper introduces EAL-GAN, a novel supervised anomaly detection method combining conditional GANs, ensemble learning, and active learning to address class imbalance and labeling costs, outperforming state-of-the-art techniques.

Contribution

The paper proposes EAL-GAN, a new architecture integrating conditional GANs, ensemble loss, and active learning for improved supervised anomaly detection.

Findings

EAL-GAN outperforms existing methods on multiple benchmarks.

The ensemble loss function effectively mitigates class imbalance.

Active learning reduces labeling costs significantly.

Abstract

Anomaly detection has wide applications in machine intelligence but is still a difficult unsolved problem. Major challenges include the rarity of labeled anomalies and it is a class highly imbalanced problem. Traditional unsupervised anomaly detectors are suboptimal while supervised models can easily make biased predictions towards normal data. In this paper, we present a new supervised anomaly detector through introducing the novel Ensemble Active Learning Generative Adversarial Network (EAL-GAN). EAL-GAN is a conditional GAN having a unique one generator vs. multiple discriminators architecture where anomaly detection is implemented by an auxiliary classifier of the discriminator. In addition to using the conditional GAN to generate class balanced supplementary training data, an innovative ensemble learning loss function ensuring each discriminator makes up for the deficiencies of the others is designed to overcome the class imbalanced problem, and an active learning algorithm is introduced to significantly reduce the cost of labeling real-world data. We present extensive experimental results to demonstrate that the new anomaly detector consistently outperforms a variety of SOTA methods by significant margins. The codes are available on Github.